EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MARD-Mol: a hybrid autoregressive-diffusion paradigm for coarse-grained molecular modeling

Sizhe Zhang, Gang Luo, Wei Fan, Xiaoyi Lv iD, Min Li iD

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btag586 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Sizhe Zhang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Central South University, Changsha, 410083, China. Hauptthemen laut MEDLINE: Models, Molecular, Drug Discovery, Computational Biology, Software. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hunan Provincial Natural Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Deep generative models have transformed drug molecule generation. However, molecules exhibit complex hierarchical structures, requiring models to simultaneously balance macroscopic topological coherence and microscopic chemical self-consistency. Although autoregressive (AR) and discrete diffusion paradigms are highly complementary, integrating their advantages within a unified architecture remains severely limited by traditional “atom-by-atom” fine-grained modeling. Results We propose MARD-Mol, a hybrid AR-diffusion framework based on motif-inspired units. By elevating the representation granularity from atoms to motif-inspired units and introducing a dual-stream hierarchical attention mechanism, it couples inter-unit AR global scaffold planning with intra-unit discrete diffusion generation. To support goal-directed drug discovery, we reformulate property optimization into an iterative “diagnose-and-repair” process, enabling targeted optimization of defective motifs while preserving the global scaffold. Extensive experiments demonstrate that MARD-Mol achieves an 86.0% Quality score in de novo generation and exhibits superior performance in fragment-constrained and multi-objective optimization, establishing a new paradigm for high-quality drug design. Availability and implementation The source code and datasets used in this study are available at GitHub: https://github.com/CSUBioGroup/MARD-Mol.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Models, MolecularDrug DiscoveryComputational BiologySoftwareAlgorithmsDrug DesignDiffusion

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Central South University, Changsha, 410083, China.
  • School of Computer Science, University of Auckland, Auckland, 1010, New Zealand.
  • School of Software, Xinjiang University, Urumqi, 830091, China.

ORCID-Profile: Xiaoyi Lv, Min Li

Förderung

  • Hunan Provincial Natural Science Foundation

Zitieren

APA

Zhang, S., Luo, G., Fan, W., Lv, X., & Li, M. (2026). MARD-Mol: a hybrid autoregressive-diffusion paradigm for coarse-grained molecular modeling. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag586

Vancouver

Zhang S, Luo G, Fan W, Lv X, Li M. MARD-Mol: a hybrid autoregressive-diffusion paradigm for coarse-grained molecular modeling. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag586

BibTeX
@article{Zhang2026,
  author = {Zhang, Sizhe and Luo, Gang and Fan, Wei and Lv, Xiaoyi and Li, Min},
  title = {MARD-Mol: a hybrid autoregressive-diffusion paradigm for coarse-grained molecular modeling},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag586}
}
Kostenlos starten →